Research map / 3D vision / Face and shape
Multi-Person Implicit Reconstruction From a Single Image
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use the proposed model-free reconstruction instead of PiFUHD | Single-person reconstruction · MPSD | CD: 1.66 -> 1.47 | Helped |
| Use the proposed model-free reconstruction instead of PHOSA | Multi-person reconstruction · CVSSP3D | CD: 7.73 -> 1.97 | Helped |
| Add occlusion silhouette loss and implicit refinement (ablation) | Voxel reconstruction on MPSD · MPSD | CD: 2.11 -> 1.47 | Helped |
| Add implicit refinement (ablation) | Voxel reconstruction on MPSD · MPSD | CD: 1.98 -> 1.47 | Helped |
| Add occlusion silhouette loss (ablation) | Voxel reconstruction on MPSD · MPSD | CD: 1.63 -> 1.47 | Helped |
| Add RGB features to implicit refinement using 3D and depth features (ablation) | Implicit refinement on MPSD · MPSD | CD: 1.71 -> 1.47 | Helped |
| Add depth features to implicit refinement using 3D and RGB features (ablation) | Implicit refinement on MPSD · MPSD | CD: 1.65 -> 1.47 | Helped |
| Use the proposed implicit refinement instead of If-net (ablation) | Implicit refinement on MPSD · MPSD | CD: 1.78 -> 1.47 | Helped |
| Add occlusion silhouette loss and implicit refinement (ablation) | Voxel reconstruction on MPSD · MPSD | 3DIoU: 61% -> 71% | Helped |
| Add implicit refinement (ablation) | Voxel reconstruction on MPSD · MPSD | P2S: 2.71 -> 1.88 | Helped |
| Add occlusion silhouette loss (ablation) | Voxel reconstruction on MPSD · MPSD | P2S: 2.44 -> 1.88 | Helped |
| Encode 3D voxel, RGB image, and depth features together in implicit refinement (ablation) | Implicit refinement on MPSD · MPSD | 3DIoU: 64% -> 71%; 67% -> 71% | Helped |
Closest papers by meaning
- VS: Reconstructing Clothed 3D Human from Single Image via Vertex Shift (CVPR 2024 · similarity 0.88)
- MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human Reconstruction (CVPR 2025 · similarity 0.88)
- MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild (CVPR 2024 · similarity 0.88)
- D^3-Human: Dynamic Disentangled Digital Human from Monocular Video (CVPR 2025 · similarity 0.88)
- HiLo: Detailed and Robust 3D Clothed Human Reconstruction with High-and Low-Frequency Information of Parametric Models (CVPR 2024 · similarity 0.88)
- DeClotH: Decomposable 3D Cloth and Human Body Reconstruction from a Single Image (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.